Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2573 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.5201. Min Act: -0.1700

Data Index: 1707875 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4368. Min Act: -0.1700

Data Index: 3118343 (Open Web Text)

Max Activating Token Index: 128

Text #2

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4279. Min Act: -0.1700

Data Index: 8809158 (Open Web Text)

Max Activating Token Index: 718

Text #3

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4486. Min Act: -0.1700

Data Index: 2224381 (Open Web Text)

Max Activating Token Index: 608

Text #4

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4105. Min Act: -0.1700

Data Index: 3265305 (Open Web Text)

Max Activating Token Index: 870

Text #5

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4280. Min Act: -0.1700

Data Index: 3413468 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4167. Min Act: -0.1700

Data Index: 1843484 (Open Web Text)

Max Activating Token Index: 647

Text #7

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4007. Min Act: -0.1700

Data Index: 598771 (Open Web Text)

Max Activating Token Index: 761

Text #8

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4064. Min Act: -0.1700

Data Index: 7475250 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4269. Min Act: -0.1700

Data Index: 181261 (Open Web Text)

Max Activating Token Index: 547

Text #10

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3994. Min Act: -0.1700

Data Index: 2061170 (Open Web Text)

Max Activating Token Index: 116

Text #11

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3706. Min Act: -0.1700

Data Index: 7202838 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3864. Min Act: -0.1700

Data Index: 5644768 (Open Web Text)

Max Activating Token Index: 369

Text #13

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3854. Min Act: -0.1700

Data Index: 3867218 (Open Web Text)

Max Activating Token Index: 58

Text #14

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3707. Min Act: -0.1700

Data Index: 535531 (Open Web Text)

Max Activating Token Index: 144

Text #15

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3570. Min Act: -0.1700

Data Index: 4604313 (Open Web Text)

Max Activating Token Index: 317

Text #16

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3435. Min Act: -0.1700

Data Index: 7010988 (Open Web Text)

Max Activating Token Index: 212

Text #17

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3567. Min Act: -0.1700

Data Index: 4181597 (Open Web Text)

Max Activating Token Index: 112

Text #18

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3351. Min Act: -0.1700

Data Index: 5162724 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3335. Min Act: -0.1700

Data Index: 5998429 (Open Web Text)

Max Activating Token Index: 260